biostudies-literatureTai JChang Gung Memorial Hospital267https://www.ebi.ac.uk/biostudies/studies/S-EPMC12840080biostudies-literatureUnknown16(2)<b>Background:</b> Liver steatosis assessment by 2D ultrasound is widely used but remains subjective. We previously developed a deep learning (DL) algorithm for objective steatosis quantification. This study aimed to (1) establish histology-based cutoffs, (2) evaluate their transferability across different imaging views, and (3) validate performance on a new scanner not included in training. <b>Methods:</b> We retrospectively analyzed 588 ultrasound studies from 457 histology-proven cases and prospectively collected paired scans using a new scanner (Philips Affiniti 70). Images from right intercostal, left hepatic lobe, and subcostal views were processed with the DL algorithm, and mean values from 3-5 images per view were correlated with histology. <b>Results:</b> Across three views, the DDiagnostics (Basel, Switzerland)Clinical Validation of a Deep Learning-Based 2D Ultrasound Steatosis Algorithm: Cutoff Transferability, Scanner Generalizability, and Comparison with FibroScan.PMC12840080CMRPG3P0261Chang MLLu LChen CJHarrison APLin CHuang SFTai DITai JHsu THfalseClinical Validation of a Deep Learning-Based 2D Ultrasound Steatosis Algorithm: Cutoff Transferability, Scanner Generalizability, and Comparison with FibroScan.<b>Background:</b> Liver steatosis assessment by 2D ultrasound is widely used but remains subjective. We previously developed a deep learning (DL) algorithm for objective steatosis quantification. This study aimed to (1) establish histology-based cutoffs, (2) evaluate their transferability across different imaging views, and (3) validate performance on a new scanner not included in training. <b>Methods:</b> We retrospectively analyzed 588 ultrasound studies from 457 histology-proven cases and prospectively collected paired scans using a new scanner (Philips Affiniti 70). Images from right intercostal, left hepatic lobe, and subcostal views were processed with the DL algorithm, and mean values from 3-5 images per view were correlated with histology. <b>Results:</b> Across three views, the D2026-01-01T00:00:00Z2026 Jan2026-06-13T03:14:20.699Z2026-06-13T03:08:55.233ZS-EPMC128400804159424310.3390/diagnostics16020267